REVIEW 2 cited by
Clothes-Changing Person Re-identification Based On Skeleton Dynamics
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Clothes-Changing Person Re-Identification (ReID) aims to recognize the same individual across different videos captured at various times and locations. This task is particularly challenging due to changes in appearance, such as clothing, hairstyle, and accessories. We propose a Clothes-Changing ReID method that uses only skeleton data and does not use appearance features. Traditional ReID methods often depend on appearance features, leading to decreased accuracy when clothing changes. Our approach utilizes a spatio-temporal Graph Convolution Network (GCN) encoder to generate a skeleton-based descriptor for each individual. During testing, we improve accuracy by aggregating predictions from multiple segments of a video clip. Evaluated on the CCVID dataset with several different pose estimation models, our method achieves state-of-the-art performance, offering a robust and efficient solution for Clothes-Changing ReID.
Forward citations
Cited by 2 Pith papers
-
Reliability-Aware 3D Geometric Injection for Universal Person Re-identification
UniGeo adds monocular SMPL body geometry to a 2D person-ReID model through a learned gate that suppresses unreliable 3D, improving occlusion, clothing-change, and cross-modality benchmarks without hurting clean ones.
-
Try Harder: Hard Sample Generation and Learning for Clothes-Changing Person Re-ID
A multimodal framework that defines, generates, and adaptively learns hard positives and negatives reports state-of-the-art Rank-1/mAP on PRCC and LTCC.
Discussion (0). Continue with ORCID to comment.